WO2019061993A1

WO2019061993A1 - Wi-fi hotspot connection method, device and storage medium

Info

Publication number: WO2019061993A1
Application number: PCT/CN2018/076180
Authority: WO
Inventors: 金新; 王建明; 肖京
Original assignee: 平安科技（深圳）有限公司
Priority date: 2017-09-26
Filing date: 2018-02-10
Publication date: 2019-04-04
Also published as: CN107835520B; CN107835520A

Abstract

A Wi-Fi hotspot connection method, a device and a storage medium. The method comprises: receiving a plurality of available Wi-Fi hotspots scanned by a client, and historical data of the plurality of Wi-Fi hotspots within a first preset time; updating a predetermined logistic regression model every second preset time; calculating first scores of the plurality of Wi-Fi hotspots according to the historical data within the first preset time and the updated logistic regression model; reading the number of connection failures of the plurality of Wi-Fi hotspots within a third preset time, and obtaining second scores of the plurality of Wi-Fi hotspots according to a predetermined weight reduction rule; sorting the plurality of Wi-Fi hotspots according to the signal strengths and the second scores of the plurality of Wi-Fi hotspots; and sequentially trying to connect the plurality of Wi-Fi hotspots according to the sorting result. The present application uses the historical data of the Wi-Fi hotspots to select an optimal Wi-Fi hotspot for the user, improving the user's internet browsing experience.

Description

Wifi hotspot connection method, device and storage medium

Priority claim

The present application is based on the priority of the Chinese Patent Application filed on September 26, 2017, filed on September 26, 2017, with the application number of CN201710884576.2, entitled "wifi hotspot connection method, device and storage medium", the overall content of the Chinese patent application This application is incorporated by reference.

Technical field

The present application relates to the field of computer technologies, and in particular, to a wifi hotspot connection method, an electronic device, and a computer readable storage medium.

Background technique

When the mobile terminal starts the wireless local area network function, the scanned wifi hotspot is displayed in the wireless local area network interface, and the user can manually connect the scanned wifi hotspot. If there is a connected wifi hotspot in the scanned hot spot, the system can The wifi hotspot automatically connects. Wifi hotspots usually have a connection password to prevent the network and ensure communication security. In the wifi hotspot connection process, a password is required for the wifi hotspot with the password.

According to the location of the mobile terminal, there may be free wifi hotspots in the scanned list of wifi hotspots, such as: operator wifi hotspot (China Mobile, China Telecom, China Unicom), public wifi, merchant wifi hotspot, etc. The user usually selects and manually connects to the scanned free wifi hotspot. The wifi hotspot that causes the connection is usually not optimal, and the manual connection is not convenient enough to affect the user's online experience. Therefore, how to select a good wifi hotspot for the user to connect automatically is a very valuable and urgent problem to be solved.

Summary of the invention

The application provides a wifi hotspot connection method, an electronic device and a computer readable storage medium, the main purpose of which is to use the historical data of the wifi hotspot to calculate the score of the wifi hotspot using the real-time updated model, and select the optimal wifi hotspot for the user. And connect operations to enhance the user's online experience.

To achieve the above objective, the present application provides a wifi hotspot connection method, and the method includes:

Receiving step: receiving, by the client, the available plurality of wifi hotspots and the historical data of the plurality of wifi hotspots in the first preset time;

a model updating step: updating the predetermined logistic regression model by using historical data of the plurality of wifi hotspots in the second preset time every second preset time, and updating the model of the logistic regression model The file is saved to the memory;

a scoring step: calculating a first score of the plurality of wifi hotspots according to historical data in the first preset time period and the updated logistic regression model;

a score adjustment step of: reading a number of connection failures of the plurality of wifi hotspots in a third preset time, and adjusting a first score of the plurality of wifi hotspots according to a predetermined decrement rule to obtain the plurality of The second rating of the wifi hotspot;

a sorting step of: sorting the plurality of wifi hotspots according to a signal strength of the plurality of wifi hotspots and a level of the second grading; and

Connection step: sequentially try to connect the plurality of wifi hotspots according to the sorting result.

Preferably, the method further comprises the steps of:

After the client successfully connects to a wifi hotspot in the fourth preset time, it is detected whether the wifi hotspot is really available. If the wifi hotspot is unavailable, the wifi hotspot after the wifi hotspot is continuously connected.

In addition, in order to achieve the above object, the present application further provides an electronic device, including: a memory, a processor, and a wifi hotspot connection program stored on the memory, where the wifi hotspot connection program is executed by the processor Implement the following steps:

In addition, in order to achieve the above object, the present application further provides a computer readable storage medium, where the wifi hotspot connection program is stored on the computer readable storage medium, and the wifi hotspot connection program is executed by the processor to implement the foregoing The steps of the wifi hotspot connection method.

Compared with the prior art, the wifi hotspot connection method, the electronic device and the computer readable storage medium proposed by the present application calculate the probability that the wifi hotspot may be successfully connected in the future by acquiring the historical data of the wifi hotspot, and then according to the wifi hotspot signal strength. The score points are used to sort the wifi hotspots, and finally the user selects the optimal wifi hotspot and performs the connection operation to improve the user's online experience.

DRAWINGS

1 is a schematic diagram of a preferred embodiment of an electronic device of the present application;

2 is a schematic block diagram of a preferred embodiment of the wifi hotspot connection procedure of FIG. 1;

FIG. 3 is a flowchart of a preferred embodiment of a method for connecting a WiFi hotspot according to the present application.

The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings.

Detailed ways

It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

The application provides an electronic device 1 . Referring to FIG. 1 , it is a schematic diagram of a preferred embodiment of the electronic device 1 of the present application. In the embodiment, the electronic device 1 includes a memory 11, a processor 12, a network interface 13, and a communication bus 14.

The electronic device 1 may be a terminal device having a computing function, such as a server, a smart phone, a tablet computer, a portable computer, a desktop computer, etc., in some embodiments, the server may be a rack server, a blade server, or a tower. Server or rack server, etc.

The network interface 13 may include a standard wired interface, a wireless interface (such as a WI-FI interface). Usually used to connect to the client (not shown in Figure 1). In the embodiment, the electronic device 1 connects the plurality of clients 2 through the network interface 13. The client 2 can be a terminal device with a wireless local area network configuration such as a notebook, a tablet, a smart phone, or an e-book reader.

Communication bus 14 is used to implement connection communication between these components.

The memory 11 includes at least one type of readable storage medium. The at least one type of readable storage medium may be a non-volatile storage medium such as a flash memory, a hard disk, a multimedia card, a card type memory, or the like. In some embodiments, the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1. In other embodiments, the readable storage medium may also be an external storage device of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (SMC). , Secure Digital (SD) card, Flash Card, etc.

In this embodiment, the readable storage medium of the memory 11 is generally used to store a wifi hotspot connection program installed on the electronic device 1, a recently connected wifi hotspot collected by the client 2, and historical data of the user, in advance. Determine good and updated logistic regression models, etc. The memory 11 can also be used to temporarily store data that has been output or is about to be output.

The processor 12, in some embodiments, may be a Central Processing Unit (CPU), a microprocessor or other data processing chip for running program code or processing data stored in the memory 11, such as performing a wifi hotspot connection. Programs, etc.

1 shows only the electronic device 1 having the components 11-14 and the wifi hotspot connection program 10, but it should be understood that not all illustrated components may be implemented, and more or fewer components may be implemented instead.

Optionally, the electronic device 1 may further include a user interface, and the user interface may include an input unit such as a keyboard, and the optional user interface may further include a standard wired interface and a wireless interface.

Optionally, the electronic device 1 may further include a display, and in some embodiments, an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch sensor. . The display is used to display information processed in the electronic device and a user interface for displaying visualizations.

Optionally, the electronic device 1 may further include a camera, an RF (Radio Frequency) circuit, a sensor, an audio circuit, a wifi module, and the like, and details are not described herein.

In the apparatus embodiment shown in FIG. 1, a wifi hotspot connection program 10 is stored in the memory 11 as a computer storage medium. When the processor 12 executes the wifi hotspot connection program 10 stored in the memory 11, the following steps are implemented:

Receiving step: receiving the available plurality of wifi hotspots scanned by the client 2 and the historical data of the plurality of wifi hotspots in the first preset time.

For example, the client 2 used by each user is installed with the client 2 version of the wifi hotspot connection program (hereinafter referred to as APP), and the client 2 performs the connection wifi hotspot operation through the APP. The APP continuously scans the plurality of wifi hotspots available at the current location through the client 2, and the electronic device 1 receives the plurality of wifi hotspots scanned by the APP through the client 2, and collects the users for the first preset time (nearly three months). The historical data of the multiple wifi hotspots accessed in the system, including: the name of the wifi, the time of the accessed time, the operation status (connection success, connection failure, login success, login failure, etc.), the frequency of access, whether the operator Provide and so on. The electronic device 1 uploads the historical data to the log server, and extracts key historical data, such as wifi identification, time, location, connection operation, online time length, connection success times, and the like, through the data warehouse technology (Extract-Transform-Load, ETL). The number of connection failures, the number of retries, the number of successful logins, the number of failed logins, etc., are saved in the memory 11 for subsequent model update and scoring operations.

a model updating step: updating the predetermined logistic regression model by using historical data of the plurality of wifi hotspots in the second preset time every second preset time, and updating the model of the logistic regression model The file is saved to memory.

Specifically, the predetermined logistic regression model is obtained by offline training: analyzing the key data, constructing a model from a time dimension, an operator/share hotspot dimension, a connection/login/retry/online time statistics, and the like. Feature, determine the model label; count the frequency and data volume of the user using the wifi hotspot by month and day, determine the length of the last three months, the most recent week, plus "operator/share hotspot", "connection/login The /retry/online time dimension combines into a series of features, such as the connection success rate of the carrier in the most recent month, and the number of retries of the wifi hotspot in the most recent week. Then, the key historical data of the last three months is used as a training set, and the random forest model is trained to obtain a logistic regression model for scoring the wifi hotspot, and the model file of the logistic regression model is saved into the memory 11. There is already a mature calculation method for training the model and using it to calculate the score of each wifi hotspot, and will not be described here.

It can be understood that the advantage of the offline training model is that there is a large amount of historical data and the sample is sufficient. The advantage of the online training model is that it can use the latest data, the model can adapt to the changes of real-time data, and the online model is more accurate in the case of large data distribution and historical gap. In order to make the scores of the subsequent calculated wifi hotspots more accurate, the above-mentioned logistic regression model is updated every second preset time (for example, one day). By combining offline training and online training, the advantages of both can be taken to improve the accuracy of the model, and at the same time, the problem of too little data volume or real-time model update failure caused by network and system problems is prevented in the online environment.

In one embodiment, model training is the process of iteratively solving model parameters using sample data using an optimization algorithm. The goal of the iterative calculation of the optimization algorithm is to minimize the loss function value of the model. For the logistic regression model, we use the L-BFGS algorithm (Limited-memory Broyden–Fletcher–Goldfarb–Shanno) training in the offline environment to obtain the parameter set S0. That is, the offline model result; in the online environment, using the FTRL-Proximal algorithm (Follow The (Proximally) Regularized Leader), load the set S0 as the initial value, and use the data of the next real-time arrived wifi hotspot to perform a calculation, and the calculation result is The new parameter value set S1; and so on, when another real-time data arrives, S1 is used as an input, and the result S2 is calculated, and the latest calculation result Sn is the latest model.

The scoring step: calculating the first score of the plurality of wifi hotspots according to historical data in the first preset time and the updated logistic regression model. After receiving the plurality of wifi hotspots sent by the client 2APP, the model file of the logistic regression model is called from the memory 11, and the historical data of the plurality of wifi hotspots within three months is retrieved from the memory 11 The input model obtains a first score of the plurality of wifi hotspots, that is, a probability that the plurality of wifi hotspots may be successfully connected in the future.

a score adjustment step of: reading a number of connection failures of the plurality of wifi hotspots in a third preset time, and adjusting a first score of the plurality of wifi hotspots according to a predetermined decrement rule to obtain the plurality of The second rating of the wifi hotspot. In this embodiment, in order to further ensure the reliability of the first score of the plurality of wifi hotspots, the first score of the plurality of wifi hotspots is adjusted according to a predetermined weight reduction rule. The predetermined decrement rule includes: reading the number of connection failures of the plurality of wifi hotspots in the third preset time in the historical data; and when the number of connection failures is less than the first preset threshold, retaining the a first score of the plurality of wifi hotspots as a second score of the plurality of wifi hotspots; when the number of connection failures is greater than a first preset threshold and less than a second preset threshold, the plurality of wifi hotspots are Multiplying the first score by the first coefficient as the second score of the plurality of wifi hotspots; and, when the number of connection failures is greater than the second predetermined threshold, multiplying the first score of the plurality of wifi hotspots Taking the second coefficient as the second score of the plurality of wifi hotspots.

Taking wifi hotspots A, B, and C as an example, the first scores of wifi hotspots A, B, and C are: 9.0, 8.5, and 9.5, respectively. Assume that the third preset time is 30 min, the first preset threshold is 5, the second preset threshold is 10, the first coefficient is 0.8, the second coefficient is 0.4, and the wifi hotspots A, B, and C are read within 30 minutes. The number of connection failures is 8, 3, and 15, respectively. The number of connection failures of the wifi hotspot A within 30 minutes is greater than the first preset threshold and less than the second predetermined threshold, so the second score of the wifi hotspot A is 7.2; The number of connection failures of the wifi hotspot B within 30 minutes is less than the first preset threshold, so the second score of the wifi hotspot B is 8.5; the number of connection failures of the wifi hotspot C within 30 minutes is greater than the second preset threshold, so the wifi hotspot The second score for C is 3.8.

Specifically, there is a case that one of the plurality of wifi hotspots has no history data, and the logistic regression model cannot calculate the first score of the wifi hotspot, and cannot calculate the second score of the wifi hotspot. For this type of wifi hotspot, take the default default score or take the average of the second scores of other multiple wifi hotspots, and assign them to this type of wifi hotspot. Further, when the default score is inconsistent with the average of the second scores of the other plurality of wifi hotspots, the second score is taken as the wifi hotspot of this type with a high score.

The sorting step: sorting the plurality of wifi hotspots according to the signal strength of the plurality of wifi hotspots and the level of the second score.

It should be noted that, for the same wifi hotspot, the signal strength of different wifi hotspots scanned by different clients 2 in different locations is different, but the scores of the wifi hotspots are consistent, so it is not possible to only score according to each wifi hotspot. To sort each wifi hotspot, you also need to consider the signal strength of each wifi hotspot. Taking wifi hotspots A, B, and C as an example, according to the above-mentioned weight reduction rule, the second scores of wifi hotspots A, B, and C are: 7.2, 8.5, and 3.8, and the signal intensity intervals of wifi hotspots A and B are all at -35dbm. Between -60dbm, the signal intensity interval of the wifi hotspot C is between -60dbm and -85dbm. Specifically, the sorting step includes:

Sorting the plurality of wifi hotspots according to a sequence of strengths of the current signal strengths of the plurality of wifi hotspots (A=B>C); for two or more wifis whose current signal strength is in the same signal strength interval The hotspot is sorted according to the order of the second scores of the two or more wifi hotspots (B>A), so the final sorting result is B, A, C.

Connection step: sequentially try to connect the plurality of wifi hotspots according to the sorting result. According to the final sorting result, the electronic device sequentially connects the wifi hotspots B, A, and C according to the order of the wifi hotspots B, A, and C.

Specifically, after the client 2 successfully connects to a wifi hotspot in the fourth preset time, it is detected whether the wifi hotspot is truly available. If the wifi hotspot is unavailable, continue to connect the wifi hotspot after the wifi hotspot. . Assuming that the fourth preset time is 10s, when the client 2 successfully connects to a wifi hotspot B within 10s, it is detected whether the wifi hotspot B is actually available, for example, using the "ping" command to check whether the network of the wifi hotspot B is connected, analyzing and Determine if there is a network failure in wifi hotspot B. It can be understood that if the wifi hotspot B is not successfully connected for more than the fourth preset time 10s, or the wifi hotspot B is detected to have a network fault, it is understood that the wifi hotspot B is unavailable, and continues to the wifi hotspot after the wifi hotspot. (A, C) to perform the connection operation.

It should be noted that the first preset time to the fourth preset time, the preset default score, the predetermined weight reduction rule, and the like need to be preset parameters and rules, and the user can adjust according to actual conditions.

The electronic device 1 in this embodiment obtains a logistic regression model for calculating a wifi hotspot score in real time by acquiring historical data of a wifi hotspot, and calculates a probability that a wifi hotspot may be successfully connected in the future, and then according to the wifi hotspot signal strength and the score score. The wifi hotspots are sorted, and finally the user selects the optimal wifi hotspot and performs the connection operation to improve the user's online experience.

Optionally, in other embodiments, the wifi hotspot connection program 10 may also be divided into one or more modules, one or more modules are stored in the memory 11 and executed by one or more processors, such as the present embodiment. The processor 12 in the example executes to complete the application. A module as referred to in this application refers to a series of computer program instructions that are capable of performing a particular function.

For example, referring to FIG. 2, it is a schematic diagram of a module of the wifi hotspot connection program 10 in FIG. In this embodiment, the wifi hotspot connection program 10 can be divided into: a receiving module 110, an updating module 120, a first scoring module 130, a second scoring module 140, a sorting module 150, and a connecting module 160. The functions or operational steps implemented by the modules 110-160 are similar to the above, and are not described in detail herein, by way of example, for example:

The receiving module 110 is configured to receive, by the client, the available multiple wifi hotspots and the historical data of the multiple wifi hotspots in the first preset time;

The update module 120 is configured to update the predetermined logistic regression model by using the historical data of the plurality of wifi hotspots in the second preset time every second preset time, and the updated logistic regression model The model file is saved to the memory;

The first scoring module 130 is configured to calculate a first score of the multiple wifi hotspots according to historical data in the first preset time and the updated logistic regression model;

The second scoring module 140 is configured to read the number of connection failures of the multiple wifi hotspots in a third preset time, and adjust the first score of the multiple wifi hotspots according to a predetermined decrement rule. a second score of the plurality of wifi hotspots;

The sorting module 150 is configured to sort the plurality of wifi hotspots according to the signal strength of the plurality of wifi hotspots and the level of the second grading; and

The connection module 160 is configured to sequentially connect the plurality of wifi hotspots according to the sorting result.

In addition, the application also provides a wifi hotspot connection method. Referring to FIG. 3, it is a flowchart of the first embodiment of the wifi hotspot connection method of the present application. The method can be performed by a device that can be implemented by software and/or hardware.

In this embodiment, the wifi hotspot connection method includes: step S10, step S20, step S30, step S40, step S50, and step S60.

Step S10: Receive historical data of the plurality of available wifi hotspots scanned by the client and the plurality of wifi hotspots in the first preset time.

For example, the client version used by each user is installed with a client version of the wifi hotspot connection program (hereinafter referred to as APP), and the client connects to the wifi hotspot operation through the APP. The APP continuously scans multiple wifi hotspots available at the current location through the client, and the electronic device receives multiple wifi hotspots scanned by the APP through the client, and collects the users to access within the first preset time (nearly three months). The historical data of the plurality of wifi hotspots includes: the name of the wifi, the time of the accessed time, the operation status (connection success, connection failure, login success, login failure, etc.), frequency of access, availability by the operator, and the like. The electronic device uploads the historical data to the log server, and extracts key historical data through the data warehouse technology (ETL), such as wifi identification, time, location, connection operation, internet connection duration, number of connection successes, number of connection failures, number of retries, The number of successful logins, the number of failed logins, etc., are saved to the memory for subsequent model update and scoring operations.

Step S20: The second predetermined time is used to update the predetermined logistic regression model by using the historical data of the plurality of wifi hotspots in the second preset time, and the model file of the updated logistic regression model is to be updated. Save to memory.

Specifically, the predetermined logistic regression model is obtained by offline training: analyzing the key data, constructing a model from a time dimension, an operator/share hotspot dimension, a connection/login/retry/online time statistics, and the like. Feature, determine the model label; count the frequency and data volume of the user using the wifi hotspot by month and day, determine the length of the last three months, the most recent week, plus "operator/share hotspot", "connection/login The /retry/online time dimension combines into a series of features, such as the connection success rate of the carrier in the most recent month, and the number of retries of the wifi hotspot in the most recent week. Then, using the key historical data of the last three months as a training set, the random forest model is trained to obtain a logistic regression model for scoring the wifi hotspot, and the model file of the logistic regression model is saved into the memory. There are already mature calculation methods for training the model and using it to calculate the score of each wifi hotspot, and will not be described here.

In one embodiment, model training is the process of iteratively solving model parameters using sample data using an optimization algorithm. The goal of the iterative calculation of the optimization algorithm is to minimize the loss function value of the model. For the logistic regression model, we use the L-BFGS algorithm training in the offline environment to obtain the parameter set S0, which is the offline model result; in the online environment, the FTRL- The Proximal algorithm loads the set S0 as the initial value and uses the data of the next real-time arrived wifi hotspot to perform a calculation. The result of the calculation is a new parameter value set S1; and so on, when a real-time data arrives, S1 is used as the initial value. Input, the result S2 is calculated, and the latest calculation result Sn is the latest model.

Step S30: Calculate a first score of the plurality of wifi hotspots according to historical data in the first preset time period and the updated logistic regression model. After receiving the plurality of wifi hotspots sent by the client APP, calling the model file of the logistic regression model and the historical data of the plurality of wifi hotspots within three months from the memory, inputting the model into the model, and obtaining the plurality of The first score of the wifi hotspots, that is, the probability that the plurality of wifi hotspots may be successfully connected in the future.

In step S40, the number of connection failures of the plurality of wifi hotspots in the third preset time is read, and the first scores of the plurality of wifi hotspots are adjusted according to a predetermined decrement rule to obtain the plurality of wifis. The second rating of the hotspot. In this embodiment, in order to further ensure the reliability of the first score of the plurality of wifi hotspots, the first score of the plurality of wifi hotspots is adjusted according to a predetermined weight reduction rule. The predetermined decrement rule includes: reading the number of connection failures of the plurality of wifi hotspots in the third preset time in the historical data; and when the number of connection failures is less than the first preset threshold, retaining the a first score of the plurality of wifi hotspots as a second score of the plurality of wifi hotspots; when the number of connection failures is greater than a first preset threshold and less than a second preset threshold, the plurality of wifi hotspots are Multiplying the first score by the first coefficient as the second score of the plurality of wifi hotspots; and, when the number of connection failures is greater than the second predetermined threshold, multiplying the first score of the plurality of wifi hotspots Taking the second coefficient as the second score of the plurality of wifi hotspots.

Step S50: Sort the plurality of wifi hotspots according to the signal strength of the plurality of wifi hotspots and the level of the second score.

It should be noted that, for the same wifi hotspot, the signal strength of different wifi hotspots scanned by different clients in different locations is different, but the scores of the wifi hotspots are consistent, so it is not possible to rely solely on the scores of the wifi hotspots. The wifi hotspots are sorted, and the signal strength of each wifi hotspot needs to be considered. Taking wifi hotspots A, B, and C as an example, according to the above-mentioned weight reduction rule, the second scores of wifi hotspots A, B, and C are: 7.2, 8.5, and 3.8, and the signal intensity intervals of wifi hotspots A and B are all at -35dbm. Between -60dbm, the signal intensity interval of the wifi hotspot C is between -60dbm and -85dbm. Specifically, the sorting step includes:

Step S60, sequentially attempting to connect the plurality of wifi hotspots according to the sorting result. According to the final sorting result, the electronic device sequentially connects the wifi hotspots B, A, and C according to the order of the wifi hotspots B, A, and C.

Further, after the client successfully connects to a wifi hotspot in the fourth preset time, it is detected whether the wifi hotspot is actually available. If the wifi hotspot is unavailable, the wifi hotspot after the wifi hotspot is continuously connected. Assume that the fourth preset time is 10s. When the client successfully connects to a wifi hotspot B within 10s, it is detected whether the wifi hotspot B is actually available. For example, use the "ping" command to check whether the network of the wifi hotspot B is connected, analyze and determine. Whether there is a network failure in wifi hotspot B. It can be understood that if the wifi hotspot B is not successfully connected for more than the fourth preset time 10s, or the wifi hotspot B is detected to have a network fault, it is understood that the wifi hotspot B is unavailable, and continues to the wifi hotspot after the wifi hotspot. (A, C) to perform the connection operation.

The wifi hotspot connection method proposed in this embodiment obtains a logistic regression model for calculating a wifi hotspot score in real time by acquiring historical data of the wifi hotspot, and calculates a probability that the wifi hotspot may be successfully connected in the future, and then according to the wifi hotspot signal strength and the score score. Sort the wifi hotspots, and finally select the best wifi hotspots for the user and connect them to improve the user's online experience.

In addition, the embodiment of the present application further provides a computer readable storage medium, where the wifi hotspot connection program is stored, and when the wifi hotspot connection program is executed by the processor, the following operations are implemented:

The specific implementation manner of the computer readable storage medium of the present application is substantially the same as the specific implementation manner of the wifi hotspot connection method, and details are not described herein again.

It is to be understood that the term "comprises", "comprising", or any other variants thereof, is intended to encompass a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a series of elements includes those elements. It also includes other elements not explicitly listed, or elements that are inherent to such a process, device, item, or method. An element that is defined by the phrase "comprising a ..." does not exclude the presence of additional equivalent elements in the process, the device, the item, or the method that comprises the element.

The serial numbers of the embodiments of the present application are merely for the description, and do not represent the advantages and disadvantages of the embodiments. Through the description of the above embodiments, those skilled in the art can clearly understand that the foregoing embodiment method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be through hardware, but in many cases, the former is better. Implementation. Based on such understanding, the technical solution of the present application, which is essential or contributes to the prior art, may be embodied in the form of a software product stored in a storage medium (such as ROM/RAM as described above). , a disk, an optical disk, including a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the methods described in the various embodiments of the present application.

The above is only a preferred embodiment of the present application, and is not intended to limit the scope of the patent application, and the equivalent structure or equivalent process transformations made by the specification and the drawings of the present application, or directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of this application.

Claims

A wifi hotspot connection method is applied to an electronic device, and the electronic device is connected to one or more clients through a network, wherein the method includes:

Receiving step: receiving, by the client, the available plurality of wifi hotspots and the historical data of the plurality of wifi hotspots in the first preset time;

a model updating step: updating the predetermined logistic regression model by using historical data of the plurality of wifi hotspots in the second preset time every second preset time, and updating the model of the logistic regression model The file is saved to the memory;

a scoring step: calculating a first score of the plurality of wifi hotspots according to historical data in the first preset time period and the updated logistic regression model;

a score adjustment step of: reading a number of connection failures of the plurality of wifi hotspots in a third preset time, and adjusting a first score of the plurality of wifi hotspots according to a predetermined decrement rule to obtain the plurality of The second rating of the wifi hotspot;

a sorting step of: sorting the plurality of wifi hotspots according to a signal strength of the plurality of wifi hotspots and a level of the second grading; and

Connection step: sequentially try to connect the plurality of wifi hotspots according to the sorting result.
The wifi hotspot connection method according to claim 1, wherein the method further comprises the following steps:

After the client successfully connects to a wifi hotspot in the fourth preset time, it is detected whether the wifi hotspot is really available. If the wifi hotspot is unavailable, the wifi hotspot after the wifi hotspot is continuously connected.
The wifi hotspot connection method according to claim 1, wherein the predetermined weight reduction rule comprises:

Reading the number of connection failures of the plurality of wifi hotspots in the third preset time in the historical data;

When the number of connection failures is less than the first preset threshold, retaining the first score of the multiple wifi hotspots as the second score of the multiple wifi hotspots;

When the number of connection failures is greater than the first preset threshold and less than the second preset threshold, multiplying the first score of the multiple wifi hotspots by the first coefficient as the second score of the multiple wifi hotspots The first preset threshold is less than the second preset threshold; and

When the number of connection failures is greater than the second preset threshold, the first score of the plurality of wifi hotspots is multiplied by the second coefficient as a second score of the plurality of wifi hotspots.
The wifi hotspot connection method according to claim 1, wherein the sorting step comprises:

Sorting the plurality of wifi hotspots according to a sequence of strengths of current signal strengths of the plurality of wifi hotspots; and

For two or more wifi hotspots whose current signal strength is in the same signal strength interval, the ranking is performed according to the order of the second scores of the two or more wifi hotspots.
The wifi hotspot connection method according to claim 1, wherein the step of scoring further comprises:

A wifi hotspot having no historical data among the plurality of wifi hotspots is given a default score or an average score assigned to a second score of the other plurality of wifi hotspots.
The wifi hotspot connection method according to claim 5, wherein the step of scoring further comprises:

When the default score is inconsistent with the average of the second scores of the other plurality of wifi hotspots, the second score is taken as the wifi hotspot of this type with a high score.
An electronic device, comprising: a memory, a processor, wherein the memory stores a wifi hotspot connection program, and when the wifi hotspot connection program is executed by the processor, the following steps are implemented:

Receiving step: receiving, by the client, the available plurality of wifi hotspots and the historical data of the plurality of wifi hotspots in the first preset time;

a model updating step: updating the predetermined logistic regression model by using historical data of the plurality of wifi hotspots in the second preset time every second preset time, and updating the model of the logistic regression model The file is saved to the memory;

a scoring step: calculating a first score of the plurality of wifi hotspots according to historical data in the first preset time period and the updated logistic regression model;

a score adjustment step of: reading a number of connection failures of the plurality of wifi hotspots in a third preset time, and adjusting a first score of the plurality of wifi hotspots according to a predetermined decrement rule to obtain the plurality of The second rating of the wifi hotspot;

Sorting step: sorting the plurality of wifi hotspots according to signal strength of the plurality of wifi hotspots and a level of the second grading; and

Connection step: sequentially try to connect the plurality of wifi hotspots according to the sorting result.
The electronic device according to claim 6, wherein when the wifi hotspot connection program is executed by the processor, the following steps are further implemented:

After the client successfully connects to a wifi hotspot in the fourth preset time, it is detected whether the wifi hotspot is really available. If the wifi hotspot is unavailable, the wifi hotspot after the wifi hotspot is continuously connected.
The electronic device according to claim 6, wherein the predetermined weight reduction rule comprises:

Reading the number of connection failures of the plurality of wifi hotspots in the third preset time in the historical data;

When the number of connection failures is less than the first preset threshold, retaining the first score of the multiple wifi hotspots as the second score of the multiple wifi hotspots;

When the number of connection failures is greater than the first preset threshold and less than the second preset threshold, multiplying the first score of the multiple wifi hotspots by the first coefficient as the second score of the multiple wifi hotspots ;and

When the number of connection failures is greater than the second preset threshold, the first score of the plurality of wifi hotspots is multiplied by the second coefficient as a second score of the plurality of wifi hotspots.
The electronic device according to claim 6, wherein the sorting step comprises:

Sorting the plurality of wifi hotspots according to a sequence of strengths of current signal strengths of the plurality of wifi hotspots; and

For two or more wifi hotspots whose current signal strength is in the same signal strength interval, the ranking is performed according to the order of the second scores of the two or more wifi hotspots.
The electronic device according to claim 6, wherein the step of scoring further comprises:

A wifi hotspot having no historical data among the plurality of wifi hotspots is given a default score or an average score assigned to a second score of the other plurality of wifi hotspots.
The electronic device according to claim 11, wherein the step of scoring further comprises:

When the default score is inconsistent with the average of the second scores of the other plurality of wifi hotspots, the second score is taken as the wifi hotspot of this type with a high score.
A computer readable storage medium, wherein the computer readable storage medium stores a wifi hotspot connection program, and when the wifi hotspot connection program is executed by the processor, the following steps are implemented:

Receiving step: receiving, by the client, the available plurality of wifi hotspots and the historical data of the plurality of wifi hotspots in the first preset time;

a model updating step: updating the predetermined logistic regression model by using historical data of the plurality of wifi hotspots in the second preset time every second preset time, and updating the model of the logistic regression model The file is saved to the memory;

a scoring step: calculating a first score of the plurality of wifi hotspots according to historical data in the first preset time period and the updated logistic regression model;

a score adjustment step of: reading a number of connection failures of the plurality of wifi hotspots in a third preset time, and adjusting a first score of the plurality of wifi hotspots according to a predetermined decrement rule to obtain the plurality of The second rating of the wifi hotspot;

a sorting step of: sorting the plurality of wifi hotspots according to a signal strength of the plurality of wifi hotspots and a level of the second grading; and

Connection step: sequentially try to connect the plurality of wifi hotspots according to the sorting result.
The computer readable storage medium according to claim 13, wherein when the wifi hotspot connection program is executed by the processor, the following steps are further implemented:

After the client successfully connects to a wifi hotspot in the fourth preset time, it is detected whether the wifi hotspot is really available. If the wifi hotspot is unavailable, the wifi hotspot after the wifi hotspot is continuously connected.
The computer readable storage medium of claim 13, wherein the predetermined weight reduction rule comprises:

Reading the number of connection failures of the plurality of wifi hotspots in the third preset time in the historical data;

When the number of connection failures is less than the first preset threshold, retaining the first score of the multiple wifi hotspots as the second score of the multiple wifi hotspots;

When the number of connection failures is greater than the first preset threshold and less than the second preset threshold, multiplying the first score of the multiple wifi hotspots by the first coefficient as the second score of the multiple wifi hotspots ;and

When the number of connection failures is greater than a second preset threshold, the first score of the plurality of wifi hotspots is multiplied by a second coefficient as a second score of the plurality of wifi hotspots.
The computer readable storage medium of claim 13, wherein the ordering step comprises:

Sorting the plurality of wifi hotspots according to a sequence of strengths of current signal strengths of the plurality of wifi hotspots; and

For two or more wifi hotspots whose current signal strength is in the same signal strength interval, the ranking is performed according to the order of the second scores of the two or more wifi hotspots.
The computer readable storage medium of claim 13, wherein the step of scoring further comprises:

A wifi hotspot having no historical data among the plurality of wifi hotspots is given a default score or an average score assigned to a second score of the other plurality of wifi hotspots.
The computer readable storage medium of claim 17, wherein the step of scoring further comprises:

When the default score is inconsistent with the average of the second scores of the other plurality of wifi hotspots, the second score is taken as the wifi hotspot of this type with a high score.
A wifi hotspot connection program is characterized in that the program comprises: a receiving module, an updating module, a first scoring module, a second scoring module, a sorting module and a connecting module.
The wifi hotspot connection program according to claim 19, wherein the step of the wifi hotspot connection method according to any one of claims 1 to 6 is implemented when the wifi hotspot connection program is executed by the processor.